Add lru_cache for last 20 questions

app.py

@@ -9,6 +9,7 @@ from huggingface_hub import login
 from smolagents import CodeAgent, InferenceClientModel
 from tools import DuckDuckGoSearchTool, WeatherInfoTool, HubStatsTool
 from retriever import load_guest_dataset
+from functools import lru_cache
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -38,7 +39,13 @@ class BasicAgent:
             model=self.model,
             max_steps=5  # Limit reasoning steps
         )
+
     def __call__(self, question: str) -> str:
+        # This just calls the cached version
+        return self._run_with_cache(question)
+
+    @lru_cache(maxsize=20) 
+    def _run_with_cache(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
         #fixed_answer = "This is a default answer."
         #print(f"Agent returning fixed answer: {fixed_answer}")